Skip to content

Data cleaning #268

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Rathinavel706 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Data cleaning #268

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
66 changes: 66 additions & 0 deletions Data cleaning using Pandas
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,66 @@
import pandas as pd
import numpy as np


print("/// 1. Initial Data Setup (with Issues)///")


data = {
'Name': ['Alice', 'Bob', 'Charlie', 'Bob', 'Eve', 'David'],
'Age': [25, 30, np.nan, 30, 45, 22],
'Sales_Amount': ['1,500 USD', '800 USD', '1200 USD', '800 USD', '3,200 USD', '450 USD'],
'Category': [' Fruit ', 'Vegetable', 'Fruit', 'Vegetable', 'VEGETABLE', ' Dairy '],
'Join_Date': ['2023-01-15', '2022-11-01', '2023-05-20', '2022-11-01', '2023-03-10', '2023-07-25']
}

df = pd.DataFrame(data)
print("\nOriginal DataFrame (Before Cleaning):")
print(df)

print("\nData Types (Before Cleaning):")
print(df.dtypes)
print("-" * 50)

print("/// Handling Missing Values ('Age' Column)")

median_age = df['Age'].median()
df['Age'] = df['Age'].fillna(median_age)
print(f"\nMissing values in 'Age' filled with Median Age: {median_age}")
print("\nDataFrame after Missing Value Handling:")
print(df)
print("-" * 50)

print("/// Removing Duplicate Rows")
print(f"\nNumber of duplicate rows found: {df.duplicated().sum()}")
df.drop_duplicates(inplace=True)
print("\nDataFrame after Removing Duplicates:")
print(df)
print(f"\nNumber of rows after removing duplicates: {len(df)}")
print("-" * 50)

print("///Correcting Data Types ('Sales_Amount', 'Join_Date')")

print("\nOriginal 'Sales_Amount' data type:", df['Sales_Amount'].dtype)

df['Sales_Amount'] = df['Sales_Amount'].str.replace(',', '').str.replace(' USD', '')

df['Sales_Amount'] = df['Sales_Amount'].astype(float)

print("New 'Sales_Amount' data type:", df['Sales_Amount'].dtype)

df['Join_Date'] = pd.to_datetime(df['Join_Date'])

print("New 'Join_Date' data type:", df['Join_Date'].dtype)

print("\nDataFrame after Data Type Corrections:")
print(df)
print("-" * 50)

print("//// Standardizing Text ('Category' Column)")
df['Category'] = df['Category'].str.strip()
df['Category'] = df['Category'].str.lower()

print("\nUnique values in 'Category' before standardization:")
print(f"\nUnique values in 'Category' after standardization: {df['Category'].unique()}")

print("